Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 2031
    Prev
    Next
    INDEX
    Explanations

    factors related to compensation claims for personal injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¸µà¸Ľ
    -0.15
     Accum
    -0.15
    еви
    -0.15
    жи
    -0.14
    æ³ķ人
    -0.14
    _suspend
    -0.14
     Renew
    -0.14
    curring
    -0.14
     accred
    -0.14
    arent
    -0.14
    POSITIVE LOGITS
     compensation
    0.52
    comp
    0.45
    -comp
    0.44
     Compensation
    0.42
    Comp
    0.42
     comp
    0.38
     compens
    0.37
     compensate
    0.37
     комп
    0.36
    _comp
    0.36
    Activations Density 0.115%

    No Known Activations